GGUF models by tensorblock

4944 GGUF models quantized by tensorblock on Hugging Face. Sizes run from 1M to 72.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
CY
Cydonia v1.3 Magnum v4 22B
Cydonia · tensorblock
Params22.2B
Context32K
Smallest8.3 GB
Tool use
DE
DeepSeek R1 Distill Qwen 32B Japanese
DeepSeek · tensorblock
Params32.8B
Context128K
Smallest12.3 GB
ReasoningTool use
HU
FreedomIntelligence HuatuoGPT2 7B
Huatuogpt · tensorblock
Params7.51B
Context4K
Smallest3.0 GB
GGUF
QW
Qwen Qwen2.5 Coder 0.5B
Qwen · tensorblock
Params494M
Context32K
Smallest0.3 GB
CodingTool use
GE
hyokwan familidata gemma7b
Gemma · tensorblock
Params8.54B
Context8K
Smallest3.5 GB
GGUF
SF
sft ds 140k
Sft · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
ML
Mlfoundations Dev DCFT Stratos Unverified 114k 32B
Mlfoundations · tensorblock
Params32.8B
Context32K
Smallest12.3 GB
Tool use
TI
TinyLlama Fitness Instructor
Tinyllama · tensorblock
Params1.1B
Context2K
Smallest0.4 GB
GGUF
GR
Ibm Granite Granite 8b Code Instruct 4k
Granite · tensorblock
Params8.05B
Context4K
Smallest3.1 GB
CodingTool use
LL
LLM4Binary Llm4Decompile 1.3b v2
Llm · tensorblock
Params1.35B
Context16K
Smallest0.6 GB
GGUF
GA
TachyHealth Gazal R1 32B Sft Merged Preview
Gazal · tensorblock
Params32.8B
Context40K
Smallest12.3 GB
ReasoningTool use
MI
dolphin 2.1 mistral 7b
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
LL
Aisingapore Llama SEA LION v3 70B IT
Llama · tensorblock
Params70.6B
Context128K
Smallest26.4 GB
Tool use
GR
Ibm Granite Granite 3.2 2b Instruct
Granite · tensorblock
Params2.53B
Context128K
Smallest1.0 GB
Tool use
QW
Qwen Qwen2.5 14B Instruct 1M
Qwen · tensorblock
Params14.8B
Context986K
Smallest5.8 GB
Tool use
LL
llm4decompile 6.7b v2
Llm · tensorblock
Params6.74B
Context8K
Smallest2.5 GB
GGUF
MI
Mistral 7B v0.1
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
PH
phi 4
Phi · tensorblock
Params14.7B
Context16K
Smallest5.5 GB
Coding
SM
HuggingFaceTB SmolLM2 1.7B Instruct
SmolLM · tensorblock
Params1.71B
Context8K
Smallest0.7 GB
GGUF
QW
Qwen Qwen2.5 Coder 7B
Qwen · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
CodingTool use
ST
Stabilityai Stablelm 3b 4e1t
Stablelm · tensorblock
Params2.8B
Context4K
Smallest1.1 GB
Coding
LL
TsinghuaC3I Llama 3 8B UltraMedical
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
TI
TinyLlama TinyLlama 1.1B Intermediate Step 1431k 3T
Tinyllama · tensorblock
Params1.1B
Context2K
Smallest0.4 GB
Coding
SM
Bitnet SmolLM 135M
SmolLM · tensorblock
Params66M
Context768
Smallest0.0 GB
GGUF
LL
openbuddy llama3 70b v21.2 32k
Llama · tensorblock
Params70.6B
Context128K
Smallest26.4 GB
GGUF
LL
Llamafactory Tiny Random Llama 3
Llama · tensorblock
Params4M
Context4K
Smallest0.0 GB
GGUF
MI
mychen76 mistral7b ocr to json v1
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
FA
FastApply 7B v1.0
Fastapply · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
GGUF
QW
Qwen1.5 0.5B
Qwen · tensorblock
Params464M
Context32K
Smallest0.2 GB
GGUF
MI
Mistral 7B KNUT ref
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF

Keep browsing